1
|
Fainberg HP, Oldham JM, Molyneau PL, Allen RJ, Kraven LM, Fahy WA, Porte J, Braybrooke R, Saini G, Karsdal MA, Leeming DJ, Sand JMB, Triguero I, Oballa E, Wells AU, Renzoni E, Wain LV, Noth I, Maher TM, Stewart ID, Jenkins RG. Forced vital capacity trajectories in patients with idiopathic pulmonary fibrosis: a secondary analysis of a multicentre, prospective, observational cohort. Lancet Digit Health 2022; 4:e862-e872. [PMID: 36333179 DOI: 10.1016/s2589-7500(22)00173-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Revised: 08/11/2022] [Accepted: 08/25/2022] [Indexed: 11/24/2022]
Abstract
BACKGROUND Idiopathic pulmonary fibrosis is a progressive fibrotic lung disease with a variable clinical trajectory. Decline in forced vital capacity (FVC) is the main indicator of progression; however, missingness prevents long-term analysis of patterns in lung function. We aimed to identify distinct clusters of lung function trajectory among patients with idiopathic pulmonary fibrosis using machine learning techniques. METHODS We did a secondary analysis of longitudinal data on FVC collected from a cohort of patients with idiopathic pulmonary fibrosis from the PROFILE study; a multicentre, prospective, observational cohort study. We evaluated the imputation performance of conventional and machine learning techniques to impute missing data and then analysed the fully imputed dataset by unsupervised clustering using self-organising maps. We compared anthropometric features, genomic associations, serum biomarkers, and clinical outcomes between clusters. We also performed a replication of the analysis on data from a cohort of patients with idiopathic pulmonary fibrosis from an independent dataset, obtained from the Chicago Consortium. FINDINGS 415 (71%) of 581 participants recruited into the PROFILE study were eligible for further analysis. An unsupervised machine learning algorithm had the lowest imputation error among tested methods, and self-organising maps identified four distinct clusters (1-4), which was confirmed by sensitivity analysis. Cluster 1 comprised 140 (34%) participants and was associated with a disease trajectory showing a linear decline in FVC over 3 years. Cluster 2 comprised 100 (24%) participants and was associated with a trajectory showing an initial improvement in FVC before subsequently decreasing. Cluster 3 comprised 113 (27%) participants and was associated with a trajectory showing an initial decline in FVC before subsequent stabilisation. Cluster 4 comprised 62 (15%) participants and was associated with a trajectory showing stable lung function. Median survival was shortest in cluster 1 (2·87 years [IQR 2·29-3·40]) and cluster 3 (2·23 years [1·75-3·84]), followed by cluster 2 (4·74 years [3·96-5·73]), and was longest in cluster 4 (5·56 years [5·18-6·62]). Baseline FEV1 to FVC ratio and concentrations of the biomarker SP-D were significantly higher in clusters 1 and 3. Similar lung function clusters with some shared anthropometric features were identified in the replication cohort. INTERPRETATION Using a data-driven unsupervised approach, we identified four clusters of lung function trajectory with distinct clinical and biochemical features. Enriching or stratifying longitudinal spirometric data into clusters might optimise evaluation of intervention efficacy during clinical trials and patient management. FUNDING National Institute for Health and Care Research, Medical Research Council, and GlaxoSmithKline.
Collapse
Affiliation(s)
- Hernan P Fainberg
- National Heart and Lung Institute, Imperial College London, London, UK.
| | - Justin M Oldham
- Division of Pulmonary and Critical Care Medicine, University of Michigan, Ann Arbor, MI, USA
| | - Philip L Molyneau
- National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Richard J Allen
- Department of Health Sciences, University of Leicester, Leicester, UK
| | - Luke M Kraven
- Department of Health Sciences, University of Leicester, Leicester, UK
| | - William A Fahy
- Discovery Medicine, GlaxoSmithKline Medicines Research Centre, Stevenage, UK
| | - Joanne Porte
- Nottingham Respiratory Research Unit, NIHR Biomedical Research Centre, University of Nottingham, Nottingham, UK
| | - Rebecca Braybrooke
- Nottingham Respiratory Research Unit, NIHR Biomedical Research Centre, University of Nottingham, Nottingham, UK
| | - Gauri Saini
- Nottingham Respiratory Research Unit, NIHR Biomedical Research Centre, University of Nottingham, Nottingham, UK
| | | | | | | | - Isaac Triguero
- Computational Optimisation and Learning Lab, School of Computer Science, University of Nottingham, Nottingham, UK; DaSCI Andalusian Institute in Data Science and Computational Intelligence, University of Granada, Granada, Spain
| | - Eunice Oballa
- Discovery Medicine, GlaxoSmithKline Medicines Research Centre, Stevenage, UK
| | - Athol U Wells
- National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Elisabetta Renzoni
- National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| | - Louise V Wain
- Department of Health Sciences, University of Leicester, Leicester, UK; National Institute for Health Research, Leicester Respiratory Biomedical Research Centre, Glenfield Hospital, Leicester, UK
| | - Imre Noth
- Pulmonary and Critical Care Medicine, University of Virginia, Charlottesville, VA, USA
| | - Toby M Maher
- National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK; Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Iain D Stewart
- National Heart and Lung Institute, Imperial College London, London, UK
| | - R Gisli Jenkins
- National Heart and Lung Institute, Imperial College London, London, UK; Royal Brompton and Harefield Hospitals, Guy's and St Thomas' NHS Foundation Trust, London, UK
| |
Collapse
|
2
|
Use of machine learning models to predict prognosis of combined pulmonary fibrosis and emphysema in a Chinese population. BMC Pulm Med 2022; 22:327. [PMID: 36038872 PMCID: PMC9422147 DOI: 10.1186/s12890-022-02124-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Accepted: 08/22/2022] [Indexed: 11/30/2022] Open
Abstract
Background Combined pulmonary fibrosis and emphysema (CPFE) is a novel clinical entity with a poor prognosis. This study aimed to develop a clinical nomogram model to predict the 1-, 2- and 3-year mortality of patients with CPFE by using the machine learning approach, and to validate the predictive ability of the interstitial lung disease-gender-age-lung physiology (ILD-GAP) model in CPFE. Methods The data of CPFE patients from January 2015 to October 2021 who met the inclusion criteria were retrospectively collected. We utilized LASSO regression and multivariable Cox regression analysis to identify the variables associated with the prognosis of CPFE and generate a nomogram. The Harrell's C index, the calibration curve and the area under the receiver operating characteristic (ROC) curve (AUC) were used to evaluate the performance of the nomogram. Then, we performed likelihood ratio test, net reclassification improvement (NRI), integrated discrimination improvement (IDI) and decision curve analysis (DCA) to compare the performance of the nomogram with that of the ILD-GAP model. Results A total of 184 patients with CPFE were enrolled. During the follow-up, 90 patients died. After screening out, diffusing lung capacity for carbon monoxide (DLCO), right ventricular diameter (RVD), C-reactive protein (CRP), and globulin were found to be associated with the prognosis of CPFE. The nomogram was then developed by incorporating the above five variables, and it showed a good performance, with a Harrell's C index of 0.757 and an AUC of 0.800 (95% CI 0.736–0.863). Moreover, the calibration plot of the nomogram showed good concordance between the prediction probabilities and the actual observations. The nomogram also improved the discrimination ability of the ILD-GAP model compared to that of the ILD-GAP model alone, and this was substantiated by the likelihood ratio test, NRI and IDI. The significant clinical utility of the nomogram was demonstrated by DCA. Conclusion Age, DLCO, RVD, CRP and globulin were identified as being significantly associated with the prognosis of CPFE in our cohort. The nomogram incorporating the 5 variables showed good performance in predicting the mortality of CPFE. In addition, although the nomogram was superior to the ILD-GAP model in the present cohort, further validation is needed to determine the clinical utility of the nomogram.
Collapse
|
3
|
Gürün Kaya A, Özyürek BA, Şahin Özdemirel T, Öz M, Erdoğan Y. Prognostic Significance of Red Cell Distribution Width in Idiopathic Pulmonary Fibrosis and Combined Pulmonary Fibrosis Emphysema. Med Princ Pract 2021; 30:154-159. [PMID: 32841950 PMCID: PMC8114038 DOI: 10.1159/000511106] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/30/2019] [Accepted: 08/24/2020] [Indexed: 12/14/2022] Open
Abstract
OBJECTIVE The red cell distribution width (RDW) is an inexpensive, readily available prognostic indicator of several diseases. RDW has been assessed as a prognostic biomarker in patients with idiopathic pulmonary fibrosis (IPF) in only one study; furthermore, the relationship between the RDW and combined pulmonary fibrosis emphysema (CPFE) has yet to be reported. SUBJECTS AND METHODS This single-center study was conducted between January 2015 and December 2018 in the Atatürk Chest Diseases and Chest Surgery Education and Research Hospital. Baseline characteristics, laboratory results, and survival status of patients were recorded. RESULTS The RDW value was significantly higher in the CPFE group than in the IPF group (median [IQR 25-75]; 16.8 [15.5-19] vs. 15.3 [13.7-16.8], p = 0.028). High RDW values were correlated with carbon monoxide diffusion capacity (DLCO) (r: -0.653 p = 0.001), 6-minute walking test (6MWT) distance (r: -0.361 p = 0.017), arterial partial oxygen pressure (PaO2) (r: -0.692 p < 0.001), and systolic pulmonary arterial pressure (SPAP) (r: 0.349 p = 0.022) in patients with fibrotic lung disease. The RDW value was significantly higher in the exitus group than in the survivors (median [IQR 25-75]; 18.4 [15.4-19] vs. 15.2 [13.5-17.2], p = 0.016). A univariate Cox regression analysis identified DLCO, SPAP, PaO2, and RDW as potential covariates of mortality. In a multivariate analysis, the DLCO (HR 1.21, 95% CI 1.11-1.47, p = 0.012) and RDW level (HR 1.65, 95% CI 1.09-2.47, p = 0.023) remained independent predictors of mortality. CONCLUSION High RDW values appear to be a simple prognostic factor in patients with IPF or CPFE.
Collapse
Affiliation(s)
- Aslıhan Gürün Kaya
- Department of Chest Diseases, Ankara University Faculty of Medicine, Ankara, Turkey,
| | - Berna Akıncı Özyürek
- Chest Diseases Clinic, Ataturk Chest Diseases and Chest Surgery Education and Research Hospital, Ankara, Turkey
| | - Tuğçe Şahin Özdemirel
- Chest Diseases Clinic, Ataturk Chest Diseases and Chest Surgery Education and Research Hospital, Ankara, Turkey
| | - Miraç Öz
- Department of Chest Diseases, Ankara University Faculty of Medicine, Ankara, Turkey
| | - Yurdanur Erdoğan
- Chest Diseases Clinic, Ataturk Chest Diseases and Chest Surgery Education and Research Hospital, Ankara, Turkey
| |
Collapse
|